摘要
网络论坛(BBS)中曝光帖的"主帖方"和"回应方"存在着典型的动态博弈行为,主导着舆情的演化进程。为了预测这种舆情的发展,以双方发帖的偏离事实程度为策略空间,设计了一种符合现实的"主帖方"和"回应方"发帖行为博弈模型,建立了基于小世界网络和元胞自动机的舆情预测模型,对现有的元胞自动机模型进行改进,用博弈策略解调节元胞自动机的迭代规则参数,实现"主帖方"和"回应方"对舆情发展的主导作用。通过仿真实验,结果表明回帖数、支持数与反对数之比等指标的变化趋势与现实中的网络事件较为吻合,说明了模型具有一定的合理性和有效性。
The post ＂master＂ and ＂respond＂ in Bulletin Board System （BBS） have a typical dynamic game behavior, and dominates the evolution of public opinion. In order to expect the evolution of public opinion,the post deviation degree from the truth is chosen as the strategy space,and a realistic ＂master＂ and ＂respond＂ post behavior game model is designed. A prediction model of public opinion based on small world network and cellular automata is established. The existing cellular automata model is improved by using game strategy to adjust the iterative rule parameter and realize the leading role of public opinion of ＂ master＂ and ＂response ＂. Simulation results show that the trend of the indexes such as the number of posts, the ratio of the number of support to opposition, etc. coincide with the network events in reality, which implies that the model is reasonable and effective.
出处
《系统仿真技术》
2014年第2期110-115,共6页
System Simulation Technology
基金
浙江省自然科学基金资助项目(13F020160)
浙江省重点实验室开放基金资助项目(ZKL-PR-200307)
浙江省教育厅科研资助项目(Y201329306)
浙江省高职高专院校专业带头人专业领军资助项目(li2013140)
关键词
网络论坛舆情预测
动态博弈
元胞自动机
小世界网络
bulletin board system public opinion prediction
dynamic game
cellular automata
small world network
